Logistic regression, random forest and XGBoost models for ICU death after non-traumatic intracerebral haemorrhage were developed in MIMIC-IV using first-24-hour data. The development cohort was 2,669 adults with 388 ICU deaths, and validation used two eICU-CRD cohorts of 396 and 1,555 patients. External AUROCs were 0.80 to 0.85, as compared to 0.78 to 0.81 for a benchmark using the Glasgow Coma Scale alone. Coagulation markers on their own discriminated weakly, with external AUROCs of 0.598 and 0.566. Adding them to the clinical model changed AUROC by 0.014 (95% CI -0.009 to 0.037) and 0.003 (-0.007 to 0.013). One validation cohort was defined narrowly for high specificity and the other more broadly, so transportability rests on how closely those definitions align.
Why it is interesting: Prediction models are rarely tested in a second database against the simplest bedside alternative. Here the multivariable models gained little on the Glasgow Coma Scale.
Abstract — the authors' own words, CC BY
Background: Intracerebral hemorrhage (ICH) is associated with high early mortality. Although routine coagulation markers are clinically relevant, their incremental value for mortality prediction beyond neurologic and physiologic information is uncertain. We developed and externally validated models using first-24-hour ICU data and evaluated the added predictive value of routine coagulation measurements.
Methods: We used MIMIC-IV for model development and eICU-CRD for external validation. The development cohort included 2,669 adults with non-traumatic ICH and 388 ICU deaths. Logistic regression, random forest, and XGBoost were evaluated using a patient-level 70:30 holdout split and 5-fold stratified cross-validation. External validation used a high-specificity primary eICU cohort (396 patients; 39 deaths) and a broader secondary hemorrhagic-stroke/likely-ICH cohort (1,555 patients; 168 deaths). Performance was assessed using AUROC, AUPRC, Brier score, calibration, and paired bootstrap comparisons. GCS-only and age-plus-GCS models served as clinical benchmarks. Coagulation-only, clinical-only, and combined XGBoost models were compared to assess incremental value.
Results: In the internal holdout cohort, AUROCs were 0.870 for logistic regression, 0.859 for random forest, and 0.867 for XGBoost. In the primary external cohort, corresponding AUROCs were 0.804, 0.839, and 0.817; AUPRCs were 0.342, 0.419, and 0.406; and Brier scores were 0.080, 0.072, and 0.074. In the broader cohort, AUROCs were 0.826, 0.848, and 0.838. Random forest showed the numerically strongest external performance, but pairwise AUROC differences among multivariable models were not clearly supported. GCS-only achieved AUROCs of 0.780 and 0.813 in the primary and broader cohorts. Coagulation-only XGBoost showed weak discrimination (AUROC 0.598 internally, 0.598 primary external, and 0.566 broader external). Adding coagulation variables to the clinical model produced AUROC differences of 0.014 (95% CI -0.009 to 0.037) and 0.003 (95% CI -0.007 to 0.013) in the two external cohorts.
Conclusions: Multivariable models based on first-24-hour ICU data retained useful discrimination across external cohorts and provided modest gains over simple GCS-based benchmarks. Routine coagulation markers alone were weak predictors and did not provide clearly supported incremental discrimination beyond broader clinical information. Cross-database transportability should be interpreted together with phenotype alignment and calibration.
Cite this item
BibTeX
Free sign-up. A digest of the new papers twice a week, grouped by domain.
Other drivers in Data, models and systems
-
Forecasts and their record
How the forecasts are made, how well they explained the past, and how well mortality can be forecast — and by whom.
None this week Earlier → -
What linked data reveals
What linked registries make it possible to know about whole populations
8 this week -
AI in medicine
Whether machine learning predicts, detects and decides better than the tools we have, and whether that has yet changed an outcome for a population.
2 this week -
Health systems and access
What the health system can provide, who gets it, and whether the gaps in health between groups are widening.
4 this week -
Value in health
What a treatment, health programme or policy is worth against what it costs, and how far the models that decide it can be trusted.
1 this week -
Revisions and new sources
What the figures are built from, what is newly available, and how much the numbers move when they are revised.
3 this week
